You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Gengliang Wang (Jira)" <ji...@apache.org> on 2021/10/06 07:44:00 UTC
[jira] [Resolved] (SPARK-36892) Disable batch fetch for a shuffle
when push based shuffle is enabled
[ https://issues.apache.org/jira/browse/SPARK-36892?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Gengliang Wang resolved SPARK-36892.
------------------------------------
Fix Version/s: 3.2.0
Resolution: Fixed
Issue resolved by pull request 34156
[https://github.com/apache/spark/pull/34156]
> Disable batch fetch for a shuffle when push based shuffle is enabled
> --------------------------------------------------------------------
>
> Key: SPARK-36892
> URL: https://issues.apache.org/jira/browse/SPARK-36892
> Project: Spark
> Issue Type: Bug
> Components: Shuffle
> Affects Versions: 3.2.0
> Reporter: Mridul Muralidharan
> Assignee: Ye Zhou
> Priority: Blocker
> Fix For: 3.2.0
>
>
> When push based shuffle is enabled, efficient fetch of merged mapper shuffle output happens.
> Unfortunately, this currently interacts badly with spark.sql.adaptive.fetchShuffleBlocksInBatch, potentially causing shuffle fetch to hang and/or duplicate data to be fetched, causing correctness issues.
> Given batch fetch does not benefit spark stages reading merged blocks when push based shuffle is enabled, ShuffleBlockFetcherIterator.doBatchFetch can be disabled when push based shuffle is enabled.
> Thx to [~Ngone51] for surfacing this issue.
> +CC [~Gengliang.Wang]
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org